一、思路
最近做了一个网站用到了从网址爬取天猫和淘宝的商品信息,首先看了下手机端的网页发现用的react,不太了解没法搞,所以就考虑从pc入口爬取数据,但是当爬取url获取数据时并没有获取价格,库存等的信息,仔细研究了下发现是异步请求了另一个接口,但是接口要使用refer才能获取数据,于是就通过以下方式写了一个简单的爬虫,用于爬取商品预览图和商品的第一个分类的价格、库存等。
二、实现
代码如下:
function crawlurl($url){
import('phpquery.curl');
$curl=new curl();
$result = $curl->read($url);
$content = mb_convert_encoding( $result['content'], 'utf-8', 'utf-8,gbk,gb2312,big5' );
$myres=array();
if(strrpos($url,'taobao.com')!=false) {
//匹配是否下架
if(strpos($content,'此宝贝已下架')!==false){
return false;
}
preg_match("|itemid : '(.*)'|isu", $content, $match);
$item_id=$match[1];
preg_match("|sellerid : '(.*)'|isu", $content, $match);
$sellet_id=$match[1];
preg_match("|<title>(.*)</title>|isu",$content,$match);
$title=$match[1];
//价格库存信息
$ch = curl_init();
curl_setopt ($ch, curlopt_url, 'https://detailskip.taobao.com/service/getdata/1/p1/item/detail/sib.htm?itemid='.$item_id.'&sellerid='.$sellet_id.'&modules=dynstock,qrcode,viewer,price,duty,xmppromotion,delivery,upp,activity,fqg,zjys,amountrestriction,couponactivity,soldquantity,originalprice,tradecontract&callback=onsibrequestsuccess');
$opt[curlopt_header]=false;
$opt[curlopt_connecttimeout]=15;
$opt[curlopt_timeout]=300;
$opt[curlopt_autoreferer]=true;
$opt[curlopt_useragent]='mozilla/5.0 (windows nt 6.1) applewebkit/536.11 (khtml, like gecko) chrome/20.0.1132.47 safari/536.11';
curl_setopt_array($ch,$opt);
curl_setopt ($ch, curlopt_returntransfer, 1);
curl_setopt ($ch,curlopt_referer,$url);
curl_setopt($ch, curlopt_ssl_verifypeer, false);
$out_put=curl_exec ($ch);
curl_close ($ch);
$res=str_replace('onsibrequestsuccess(',"",$out_put);
$res=rtrim($res,');1');
$result=json_decode($res,true);
//查询出图片信息
preg_match('|<ul id="j_ulthumb" class="tb-thumb tb-clearfix">(.*)</ul>|isu', $content, $match);
preg_match_all('/<img data-src="(.*?)" //', $match[1], $images);
$myres['title']=str_replace('-淘宝网','',$title);
$myres['price']=current($result['data']['originalprice']);
$myres['act_price']=current($result['data']['promotion']['promodata']);
$myres['stock']=$result['data']['dynstock']['stock'];
$myres['banners']=$images[1];
}else{
//匹配是否下架
if(strpos($content,'此宝贝已下架')!==false){
return false;
}
$start=strpos($url,'&id=');
$item_id=substr($url,$start+4,12);
if(!is_numeric($item_id)){
$start=strpos($url,'?id=');
$end=strpos($url,'&spm');
$item_id=substr($url,$start+4,$end-$start-4);
}
preg_match("|<title>(.*)</title>|isu",$content,$match);
$title=$match[1];
$myurl='https://mdskip.taobao.com/core/inititemdetail.htm?cachedtimestamp=1500562177777&querymemberright=true&cartenable=true&offlineshop=false&addresslevel=2&itemid='.$item_id.'&trybeforebuy=false&isareasell=false&tmallbuysupport=true&ispurchasemallpage=false&household=false&isforbidbuyitem=false&service3c=false&isregionlevel=false&showshopprom=false&isseckill=false&sellerpreview=false&isuseinventorycenter=false&isapparel=true&callback=setmdskip×tamp=1500562172109&isg=aiuldzfwmp/smgvurqsilu3ytet/zdis&isg2=ajk51jihrfqkzxminpp6dkyxskxt7iyskzstevtu9wdf4ll0o5y9ykdyethu';
//价格库存信息
$ch = curl_init();
curl_setopt ($ch, curlopt_url, $myurl);
$opt[curlopt_header]=false;
$opt[curlopt_connecttimeout]=15;
$opt[curlopt_timeout]=300;
$opt[curlopt_autoreferer]=true;
$opt[curlopt_useragent]='mozilla/5.0 (windows nt 6.1) applewebkit/536.11 (khtml, like gecko) chrome/20.0.1132.47 safari/536.11';
curl_setopt_array($ch,$opt);
curl_setopt ($ch, curlopt_returntransfer, 1);
curl_setopt ($ch,curlopt_referer,$url);
curl_setopt($ch, curlopt_ssl_verifypeer, false);
$out_put=curl_exec ($ch);
curl_close ($ch);
$res = mb_convert_encoding( $out_put, 'utf-8', 'utf-8,gbk,gb2312,big5' );
$res=str_replace('setmdskip',"",$res);
$res=str_replace('(',"",$res);
$res=str_replace(')',"",$res);
$result=json_decode($res,true);
$nowk="";
$nowstore="";
foreach($result['defaultmodel']['inventorydo']['skuquantity'] as $k=>$val){
$nowk=$k;
$nowstore=$val;
break;
}
$myres['title']=str_replace('-tmall.com天猫','',$title);
$myres['price']=$result['defaultmodel']['itempriceresultdo']['priceinfo'][$nowk]['price'];
$myres['act_price']=isset($result['defaultmodel']['itempriceresultdo']['priceinfo'][$nowk]['suggestivepromotionlist'])?$result['defaultmodel']['itempriceresultdo']['priceinfo'][$nowk]['suggestivepromotionlist']:$result['defaultmodel']['itempriceresultdo']['priceinfo'][$nowk];
$myres['stock']=$result['defaultmodel']['inventorydo']['totalquantity']?$result['defaultmodel']['inventorydo']['totalquantity']:$nowstore['quantity'];
//查询出图片信息
preg_match('|<ul id="j_ulthumb" class="tb-thumb tm-clear">(.*)</ul>|isu',$content, $match);
preg_match_all('/<img src="(.*?)" //',$match[1],$images);
$myres['banners']=$images[1];
}
return $myres;
}
上述代码用到phpquery的库,但是其实没啥用,直接用curl就行,具体爬取的数据可以穿参查看结果,方法不区分淘宝和天猫链接,但是前提是必须是pc端链接,另外正则写的不规范,所以可以自己重写正则来匹配数据。
更多内容请参考专题《python爬取功能汇总》进行学习。
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持硕编程。
【说明】:本文章由站长整理发布,文章内容不代表本站观点,如文中有侵权行为,请与本站客服联系(QQ:254677821)!